| | --- |
| | id: mirrorbert_MedRoBERTa.nl_clstoken |
| | name: mirrorbert_MedRoBERTa.nl_clstoken |
| | description: MedRoBERTa.nl continued pre-training on hard medical terms pairs from |
| | the SNOMED and UMLS ontology, using the infoNCE loss function |
| | license: gpl-3.0 |
| | language: nl |
| | tags: |
| | - biomedical |
| | - embedding |
| | - lexical semantic |
| | - entity linking |
| | - bionlp |
| | - science |
| | - biology |
| | pipeline_tag: feature-extraction |
| | --- |
| | |
| | # Model Card for Mirrorbert Medroberta.Nl Clstoken |
| |
|
| | The model was trained on about 8 millions medical entity pairs (term, synonym) |
| |
|
| |
|
| | ### Expected input and output |
| | The input should be a string of biomedical entity names, e.g., "covid infection" or "Hydroxychloroquine". The [CLS] embedding of the last layer is regarded as the output. |
| |
|
| | #### Extracting embeddings from mirrorbert_MedRoBERTa.nl_clstoken |
| |
|
| | The following script converts a list of strings (entity names) into embeddings. |
| | ```python |
| | import numpy as np |
| | import torch |
| | from tqdm.auto import tqdm |
| | from transformers import AutoTokenizer, AutoModel |
| | |
| | tokenizer = AutoTokenizer.from_pretrained("UMCU/mirrorbert_MedRoBERTa.nl_clstoken") |
| | model = AutoModel.from_pretrained("UMCU/mirrorbert_MedRoBERTa.nl_clstoken").cuda() |
| | |
| | # replace with your own list of entity names |
| | all_names = ["covid-19", "Coronavirus infection", "high fever", "Tumor of posterior wall of oropharynx"] |
| | |
| | bs = 128 # batch size during inference |
| | all_embs = [] |
| | for i in tqdm(np.arange(0, len(all_names), bs)): |
| | toks = tokenizer.batch_encode_plus(all_names[i:i+bs], |
| | padding="max_length", |
| | max_length=25, |
| | truncation=True, |
| | return_tensors="pt") |
| | toks_cuda = {} |
| | for k,v in toks.items(): |
| | toks_cuda[k] = v.cuda() |
| | cls_rep = model(**toks_cuda)[0][:,0,:] |
| | all_embs.append(cls_rep.cpu().detach().numpy()) |
| | |
| | all_embs = np.concatenate(all_embs, axis=0) |
| | ``` |
| |
|
| |
|
| | # Data description |
| |
|
| | Hard Dutch ontological synonym pairs (terms referring to the same CUI/SCUI). |
| |
|
| |
|
| | # Acknowledgement |
| |
|
| | This is part of the [DT4H project](https://www.datatools4heart.eu/). |
| |
|
| | # Doi and reference |
| |
|
| |
|
| |
|
| | For more details about training and eval, see MirrorBERT [github repo](https://github.com/cambridgeltl/mirror-bert). |
| |
|
| |
|
| | ### Citation |
| | ```bibtex |
| | @inproceedings{liu-etal-2021-fast, |
| | title = "Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders", |
| | author = "Liu, Fangyu and |
| | Vuli{'c}, Ivan and |
| | Korhonen, Anna and |
| | Collier, Nigel", |
| | booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing", |
| | month = nov, |
| | year = "2021", |
| | address = "Online and Punta Cana, Dominican Republic", |
| | publisher = "Association for Computational Linguistics", |
| | url = "https://aclanthology.org/2021.emnlp-main.109", |
| | pages = "1442--1459", |
| | } |
| | ``` |
| | For more details about training/eval and other scripts, see CardioNER [github repo](https://github.com/DataTools4Heart/CardioNER). |
| | and for more information on the background, see Datatools4Heart [Huggingface](https://huggingface.co/DT4H)/[Website](https://www.datatools4heart.eu/) |
| |
|
| |
|
| |
|
| |
|
